(21 days)
EXINI is intended to be used by trained healthcare professionals and researchers for acceptance, transfer, storage, image display, manipulation, quantification and reporting of digital medical images. The system is intended to be used with images acquired using nuclear imaging (NM) and computed tomography (CT). The software provides general Picture Archiving and Communications System (PACS) tools and a clinical application for oncology including lesion marking and analysis.
The EXINI software provides trained health-care professionals and researchers with a software tool set for acceptance, transfer, storage, image display, manipulation and quantification of digital medical images. The software is intended to be used with images acquired using nuclear imaging (NM) and computed tomography (CT) modalities. The software provides general Picture Archiving and Communications System (PACS) tools and a clinical application for markup and analysis of bone lesions in bone scans. The software complies with the Digital Imaging and Communications in Medicine (DICOM 3) standard. The software runs on a standard PC with Microsoft Windows operating system.
The provided 510(k) summary for the EXINI device states that clinical performance data was NOT conducted to support this submission. Therefore, the document does not contain information about a study proving the device meets acceptance criteria based on clinical performance.
The non-clinical performance data section refers to "verification and validation (V&V) plan including definition of test methods and acceptance criteria was designed to ensure equivalent performance with the predicate device." However, specific acceptance criteria and detailed reported performance metrics for the EXINI device regarding its image processing and analysis capabilities are not explicitly provided in the excerpt. Instead, it concludes that the non-clinical performance data shows "equal performance and raises no new questions of safety and effectiveness in comparison to the predicate device."
Without specific acceptance criteria and reported device performance from a clinical study, it's not possible to populate the table or answer most of the requested questions.
Here's a breakdown of what can be extracted and what is explicitly stated as not available:
1. A table of acceptance criteria and the reported device performance
- Not available in the provided text for clinical performance. The document states "Clinical testing was not conducted to support this 510(k) submission."
- For non-clinical performance, the document vaguely mentions "test methods and acceptance criteria was designed to ensure equivalent performance with the predicate device," but does not provide the specific criteria or reported performance metrics.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Not applicable/Not available. Since no clinical study was conducted, there is no test set for clinical performance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
- Not applicable/Not available. Since no clinical study was conducted, there's no ground truth established for a test set.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Not applicable/Not available. Since no clinical study was conducted, there's no adjudication method for a test set.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- No, an MRMC comparative effectiveness study was explicitly NOT done. The document states "Clinical testing was not conducted to support this 510(k) submission."
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- No, a standalone clinical performance study was explicitly NOT done. The document states "Clinical testing was not conducted to support this 510(k) submission." The device is described as "semi-automatic" and requires a "manual step (hotspot verification step) where the user reviews and edits the selection of hotspots." This indicates it's designed for human-in-the-loop operation, and no standalone clinical performance was assessed.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Not applicable/Not available. Since no clinical study was conducted, there is no ground truth Type established for clinical performance.
8. The sample size for the training set
- Not available. The document does not provide information about a training set since it focuses on the predicate device equivalence based on technological characteristics and non-clinical V&V. AI/ML models typically require a training set, but this document does not detail its development beyond stating it uses "image processing techniques for segmentation of skeletal regions, normalization and hotspot contouring/segmentation."
9. How the ground truth for the training set was established
- Not available. The document does not provide information about a training set or how its ground truth might have been established.
Summary of available information regarding compliance:
The EXINI device passed non-clinical performance data testing. The "verification and validation (V&V) plan including definition of test methods and acceptance criteria was designed to ensure equivalent performance with the predicate device" (IBIS Explorer and Markup Software). The V&V test results indicated that EXINI "meets its intended use, user needs and software requirements."
The conclusion is that the non-clinical performance data showed "equal performance and raises no new questions of safety and effectiveness in comparison to the predicate device." This means the device was cleared based on demonstrating substantial equivalence to a predicate device through non-clinical testing and shared technological characteristics, not through a clinical study demonstrating specific performance metrics against an established ground truth.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).